chapter_13.py 文件源码

def train_linreg(X_train, y_train, eta, epochs):
    costs = []

    eta0 = T.fscalar('eta0')
    y = T.fvector(name='y')
    X = T.fmatrix(name='X')
    w = theano.shared(
        np.zeros(shape=(X_train.shape[1] + 1), dtype=theano.config.floatX),
        name='w',
    )

    net_input = T.dot(X, w[1:]) + w[0]
    errors = y - net_input
    cost = T.sum(T.pow(errors, 2))

    gradient = T.grad(cost, wrt=w)
    update = [(w, w - (eta0 * gradient))]

    train = theano.function(
        inputs=[eta0],
        outputs=cost,
        updates=update,
        givens={X: X_train, y: y_train},
    )

    for _ in range(epochs):
        costs.append(train(eta))

    return costs, w